Interpolation Accuracy of Hybrid Soft Computing Techniques in Estimating Discharge Capacity of Triangular Labyrinth Weir

Soft Computing Techniques (SCT) are extensively used to estimate Labyrinth Weir's (LW) flow-rate. Due the multiplicity of these techniques, identifying most competent SCT is indispensable. This study aims flow-rate a sharp-crest triangular LW as function its side leg angle α and total head ratio (H/P) through several SCTs such Adaptive Neuro-Fuzzy Inference System (ANFIS), Multi-Layer Perceptron (MLP), Support Vector Regression, Radial Basis Function Neural Network. Additionally, SCTs' potential combinations with Firefly Optimization Algorithm (FA) Particle Swarm (PSO) also investigated for estimation. The conducted experimental studies on examined wide range H/P in some limited values. Correspondingly, all proposed models techniques incapable estimating flow rate intermediate values without interpolation. Therefore, SCT's Interpolation accuracy utmost importance. Besides standard evaluation testing stage, novel approach utilized evaluate interpolation task. evaluated based statistical criteria, Taylor diagram, Kruskal-Wallis, Mann-Whitney tests. It concluded that competence an stage cannot guarantee Subsequently, ANFIS-PSO MLP-FA show highest task, respectively. Eventually, according systematic investigation implemented diagnostic test results, two rankings presented applied their performance accuracy.